OneHOI unifies HOI generation and editing in one conditional diffusion transformer using role-aware tokens, structured attention, and joint training on mixed datasets to reach SOTA on both tasks.
High-resolution image syn- thesis with latent diffusion models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3verdicts
UNVERDICTED 3representative citing papers
LIFT decomposes distillation into coarse linear alignment then fine refinement while PLACE adds error-based local adaptation, allowing stable training of 1.3M-parameter students (1.6% teacher size) to FID 15.73 across diffusion and flow models.
PercHead achieves state-of-the-art single-image 3D head reconstruction and editing by replacing low-level losses with a perceptual loss from DINOv2 and SAM 2.1 inside a Vision Transformer architecture.
citing papers explorer
-
OneHOI: Unifying Human-Object Interaction Generation and Editing
OneHOI unifies HOI generation and editing in one conditional diffusion transformer using role-aware tokens, structured attention, and joint training on mixed datasets to reach SOTA on both tasks.
-
LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models
LIFT decomposes distillation into coarse linear alignment then fine refinement while PLACE adds error-based local adaptation, allowing stable training of 1.3M-parameter students (1.6% teacher size) to FID 15.73 across diffusion and flow models.
-
PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing
PercHead achieves state-of-the-art single-image 3D head reconstruction and editing by replacing low-level losses with a perceptual loss from DINOv2 and SAM 2.1 inside a Vision Transformer architecture.